• The Korean Journal of Applied Statistics
• /
• v.25 no.1
• /
• pp.197-203
• /
• 2012

In fitting a regression model, we often encounter data sets which do not follow Gaussian distribution and/or do not have equal variance. In this case estimation of the conditional density of a response variable at a given design point is hardly solved by a standard least squares method. To solve this problem, we propose a simple method to estimate the distribution of the fitted vales under heteroscedasticity using the idea of quantile regression and the histogram techniques. Application of this method to a real data sets is given.

• The Korean Journal of Applied Statistics
• /
• v.30 no.5
• /
• pp.733-745
• /
• 2017

Local composite quantile regression is a useful non-parametric regression method widely used for its high efficiency. Data smoothing methods using kernel are typically used in the estimation process with performances that rely largely on the smoothing parameter rather than the kernel. However, $L_2$-norm is generally used as criterion to estimate the performance of the regression function. In addition, many studies have been conducted on the selection of smoothing parameters that minimize mean square error (MSE) or mean integrated square error (MISE). In this paper, we explored the optimality of selecting smoothing parameters that determine the performance of non-parametric regression models using local linear composite quantile regression. As evaluation criteria for the choice of smoothing parameter, we used mean absolute error (MAE) and mean integrated absolute error (MIAE), which have not been researched extensively due to mathematical difficulties. We proved the uniqueness of the optimal smoothing parameter based on MAE and MIAE. Furthermore, we compared the optimal smoothing parameter based on the proposed criteria (MAE and MIAE) with existing criteria (MSE and MISE). In this process, the properties of the proposed method were investigated through simulation studies in various situations.

• The Korean Journal of Applied Statistics
• /
• v.31 no.3
• /
• pp.343-352
• /
• 2018

We can use quantile regression and expectile regression analysis to estimate trends in extreme regions as well as the average trends of response variables in given explanatory variables. In this paper, we compare the performance between the parametric and nonparametric methods for expectile regression. We introduce each estimation method and analyze through various simulations and the application to real data. The nonparametric model showed better results if the model is complex and difficult to deduce the relationship between variables. The use of nonparametric methods can be recommended in terms of the difficulty of assuming a parametric model in expectile regression.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.9
• /
• pp.39-49
• /
• 2020

This study empirically examines herd behavior for fast moving consumer goods (FMCG) sector stocks under varied market return conditions and the period during the global financial crisis and its aftermath. We examine the sample of stocks trading on the Nifty FMCG Index of the Indian equity market from January 2008 up to December 2018 using the dispersion measure of cross sectional absolute deviation and examine its relationship with the market return to explore herd phenomenon. Quantile regression estimate is used and the results of the study validate rational asset pricing models as the sector does not display herding. In contrast, anti-herd behavior at lower and median quantile values is observed. A possible reason can be the non-cyclical nature of the industry where investors rely more on the fundamentals rather than crowd chasing. We also findthe absence of herd phenomenon during the market asymmetries of bull and bear phases, extreme movements, the period of the global financial crisis, and afterward. We further examine herding under the impact of the information technology (IT) industry and conclude that significant return movements in IT sector impact dispersions in the FMCG industry. Also, there is a co-varying risk between the two sectors confirming the spillover in an integrated market.

• Management & Information Systems Review
• /
• v.37 no.1
• /
• pp.155-175
• /
• 2018

Lots of previous researches on determinants of apartment prices in Korea consider spatial dependence while few studies regard endogeneity of spatial lag by adding a spatial lag to an OLS regression. Thus, this study intends to include this spatial lag in its analysis of determinants of apartment price in Busan by using a two-stage quantile regression. The empirical results are : the coefficient of spatial lag variable is more than 0.5 and is statistically significant at 1% level. From this result we can confirm that the effect of the price of nearby apartment on that of another apartment is very big. We also find that apartment buyers prefer larger size, height in both the total floors and living floor, south-facing living room with a ocean view, and proximity to metros, high school and coast. Unlike our expectation, however, mountain view is less favored than building view, which we can guess is because apartments with mountain views are mostly located in the low-priced apartment area where some of their living rooms face north. Quantile regression also explains the effect of hedonic characteristics on apartment price better than OLS estimation. For instance, the effect of south facing living room variable on the price is twice larger in high-price apartments than in low-price counterparts. And the effect of vicinity to the coast or the ocean is ten times bigger in high priced apartments.

• The Korean Journal of Applied Statistics
• /
• v.25 no.5
• /
• pp.793-802
• /
• 2012

One proposal is made to construct a nonparametric estimator of slope parameters in a regression model under symmetric error distributions. This estimator is based on the use of the idea of minimizing approximate variance of a proposed estimator using regression quantiles. This nonparametric estimator and some other L-estimators are studied and compared with well known M-estimators through a simulation study.

• Communications for Statistical Applications and Methods
• /
• v.28 no.1
• /
• pp.81-88
• /
• 2021

k-least quantile of squares (k-LQS) estimates are a generalization of least median of squares (LMS) estimates. They have not been used as much as LMS because their breakdown points become small as k increases. But if the size of outliers is assumed to be fixed LQS estimates yield a good fit to the majority of data and residuals calculated from LQS estimates can be a reliable tool to detect outliers. We propose to use LQS estimates for separating a clean set from the data in the context of outlyingness of the cases. Three procedures are suggested for the identification of outliers using LQS estimates. Examples are provided to illustrate the methods. A Monte Carlo study show that proposed methods are effective.

• Research in Community and Public Health Nursing
• /
• v.24 no.3
• /
• pp.273-281
• /
• 2013

Purpose: The purpose of this study was to determine gender differences in effects of self-efficacy, exercise benefits and barriers, and demographic factors on the physical activity. Methods: Seventy sedentary office workers, 35 male and 35 female, from a major airline company, completed a questionnaire from March 28 to April 5, 2012. Steps and body mass indices were measured using a CW-700/701 (Yamax) pedometer and Inbody 720 (Biospace), respectively. Data were analyzed using t-test, $x^2$-test, multiple linear regression, and simultaneous quantile regression. Results: For male workers, exercise self-efficacy had a significant effect on physical activity, but only when respondents were at 10%(3,431 steps/day, p=.018) and 25%(4,652 steps/day, p=.044) of the physical activity distribution. For female workers, marital status was significantly related to physical activity, but only when respondents were at 10% (3,537 steps/day, p=.013) and 25%(3,862 steps/day, p=.014) of the physical activity distribution. Conclusion: Quantile regression highlights the heterogeneous effect of physical activity determinants among office workers. Therefore intervention strategies for increasing physical activity should be tailed to genders as well as physical activity levels.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.4
• /
• pp.21-32
• /
• 2021

This paper aims to investigate the relationship between country-level institutional quality and public debt in the context of Pakistan. The hypotheses of this study were assessed by using the country-level institutional quality data for Pakistan throughout the years from 1996 to 2018. Data came from the World Databank, IMF and Worldwide Governance Indicators databases. For the analysis, ordinary least square, quantile regression and robust regression were employed to assess the factors influencing the public debt. The results of this study indicate that the factors of voice and accountability, regulatory quality, and control of corruption have a positive and significant relationship with public debt, while political stability, government effectiveness, and the rule of law have a negative and significant effect on public debt. Based on the findings, a weak country-level institutional quality poses a substantial market risk as it signals the existence of an unfavorable economic condition that raises public debt. It was also revealed that an improved performance of country-level institutional quality can lead to the improvement of financial market transparency, hence reduce public debt. In contrast to previous studies, the present study will be breaking ground in enhancing public insight regarding the impact of country-level institutional quality on Pakistan's public debt.

• The Journal of the Korea Contents Association
• /
• v.16 no.5
• /
• pp.399-409
• /
• 2016

Purpose: The purpose of this study was to examine factors influencing health related quality of life(HRQOL) in patients with hypertension. Methods: This study carried out secondary analysis using the data from the $5^{th}$ Korean National Health and Nutrition Examination Survey. Subject samples who were selected are 1,240 hypertension patients. The data were analyzed by using descriptive statistics, traditional classic regression, and quantile regression. Results: Restriction of activity, depressive mood, and subjective health status had only significant effects on HRQOL(p<.001). After quantile regression, depressive mood and subjective health status had only significant at 20%(p<.001), 40%(p<.001), and 60%(p<.01) of HRQOL. Perceived stress(p<.001) and regular exercise(p<.01) had only significant at 20% of HRQOL. Current drinking status had only significant at 20%(p<.001) and 80%(p<.01) of HRQOL. Conclusions: Quantile regression maybe a better statistical tool in understanding the heterogeneous effect of hypertension patient's HRQOL as health outcome. Therefore interventions are needed for patients with hypertension to manage each of the factors affecting the patient's perceived health status by each quantile.